© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10241
    Prev
    Next
    INDEX
    Explanations

    scene graphs and geometry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (=
    -1.33
    ):
    -1.23
    、
    -1.18
     between
    -1.16
     Schiffe
    -1.15
    ˂
    -1.12
    acing
    -1.10
     to
    -1.09
     įva
    -1.09
     Bemerkungen
    -1.09
    POSITIVE LOGITS
     nostru
    1.38
     noastre
    1.35
     acestei
    1.34
     burbu
    1.30
     acestui
    1.30
    dification
    1.29
     dator
    1.28
     oamen
    1.24
     rosse
    1.15
    ม้
    1.13
    Activations Density 0.028%

    No Known Activations